Recognition and labeling of faults in wind turbines with a density-based clustering algorithm

Luo, Shuai; Liu, Hongwei; Qi, Ershi

doi:10.1108/dta-09-2020-0223

Cited by 6 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the research on clustering analysis has also received much attention. Agersted [15]. Cupak et al designed a regression method based on non hierarchical clustering analysis to address the difficulty of low flow zoning in the upstream of the Vistula River basin.…”

Section: Related Workmentioning

confidence: 99%

Enterprise intelligent manufacturing data analysis technology based on big data analysis

Wang,

Li,

Zhu

2024

Int. J. Simul. Multidisci. Des. Optim.

View full text Add to dashboard Cite

The rise of big data has deeply influenced various industries, especially the intelligent manufacturing of enterprises. However, traditional data analysis methods are difficult to adapt to the storage and analysis of sea volume data in intelligent production. To address this issue, a method relying on big data analysis and cluster analysis is proposed to design data analysis techniques for enterprise intelligent manufacturing. The proposed improved algorithm is subjected to performance testing. The accuracy of this algorithm is 97%, which exceeds the comparison algorithm. The error is 6% and the running time is 5 s, both of which are below the comparison algorithm. The effectiveness of the enterprise intelligent manufacturing data analysis technology is tested. The experimental group completes orders in 4.1 weeks, 5.2 weeks, 3 weeks, 3.4 weeks, and 4.9 weeks, respectively, shorter than the control group. The product qualification rates for the experimental group are 92%, 93%, 95%, 92%, and 92%, respectively, which exceed the control group. In summary, the proposed enterprise intelligent manufacturing data analysis technology relying on big data and cluster analysis can better utilize data resources and information technology, improving the production efficiency and competitiveness of enterprises. It is hope that this research result can provide useful guidance and reference for the application and development of intelligent manufacturing data analysis technology in enterprises.

show abstract

Section: Related Workmentioning

confidence: 99%

Enterprise intelligent manufacturing data analysis technology based on big data analysis

Wang,

Li,

Zhu

2024

Int. J. Simul. Multidisci. Des. Optim.

View full text Add to dashboard Cite

show abstract

“…Mishra et al proposed a clustering algorithm using coupling theory and fuzzy logic to address the issue of sensor node clustering reducing battery power loss. The results show that the algorithm performs better than the comparison algorithm in different scenarios [10]. Prakash's team proposed a K-means clustering algorithm based on attribute value frequency to locate appropriate random centers for the complex and limited grouping methods of highly similar agricultural data.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, it is necessary to process the weight of this feature attribute to reduce the impact on the clustering results on the one hand, while retaining the structural characteristics of the original dataset. First, the statistical dispersion judgment formula of all feature attributes is expression (10).…”

Section: B Wc-ena Based On Encm Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

The Application of Elastic Network Algorithm Based on Weighted Property in Clustering Analysis

Liu,

Cao,

Lei

et al. 2023

IEEE Access

View full text Add to dashboard Cite

With the rapid development of internet technology, the internet has provided convenience for people's lives, and people's lives and work are increasingly inseparable from the internet. However, the various types of information data in the Internet are very large, and accurately obtaining useful information from them has become particularly important. Therefore, clustering analysis technology is widely applied in various fields. The elastic network algorithm is vulnerable to noise and other factors in clustering analysis, resulting in low accuracy of clustering results. To solve this problem, this study proposes an elastic network algorithm based on weighted properties for clustering analysis. After comparative experiments, the results show that the accuracy of the proposed algorithm is 98%; The area under the precision recall curve is 0.86; The maximum F-value is 0.93; The area under the working characteristic curve of the subject is 0.94; The precision ultimately stabilized at 97%; All values are higher than the comparison algorithm. In the experiment, the running time of the algorithm was 11 seconds and the average error was 7%, both of which were lower than the comparison algorithm. When the algorithm is affected by Statistical dispersion and threshold parameters, the accuracy of the proposed algorithm is 71%, 69% and 67% respectively, which are better than the comparison algorithm. In conclusion, the elastic network algorithm based on the weighted characteristics proposed in the study has high accuracy, strong stability and advantages in clustering.

show abstract

“…The most commonly used clustering algorithm based on density is DBSCAN. Although this algorithm does not necessitate knowledge of the number of classes the data is divided into in advance, knowledge of the radius and the minimum number of points is required [29].…”

Section: Typical Clustering Algorithmmentioning

confidence: 99%

RBFNN Design Based on Modified Nearest Neighbor Clustering Algorithm for Path Tracking Control

Zheng

Jung

Kim

2021

Sensors

View full text Add to dashboard Cite

Radial basis function neural networks are a widely used type of artificial neural network. The number and centers of basis functions directly affect the accuracy and speed of radial basis function neural networks. Many studies use supervised learning algorithms to obtain these parameters, but this leads to more parameters that need to be determined, thereby making the system more complex. This study proposes a modified nearest neighbor-based clustering algorithm for training radial basis function neural networks. The calculation of this clustering algorithm is not large, and it can adapt to varying densities. Furthermore, it does not require researchers to set parameters based on experience. Simulation proves that the clustering algorithm can effectively cluster samples and optimize the abnormal samples. The radial basis function neural network based on modified nearest neighbor-based clustering has higher accuracy in curve fitting than the conventional radial basis function neural network. Finally, the path tracking control based on a radial basis function neural network of a magnetic microrobot is investigated, and its effectiveness is verified through simulation. The test accuracy and training accuracy of the radial basis function neural network was improved by 23.5% and 7.5%, respectively.

show abstract

Recognition and labeling of faults in wind turbines with a density-based clustering algorithm

Cited by 6 publications

References 37 publications

Enterprise intelligent manufacturing data analysis technology based on big data analysis

Enterprise intelligent manufacturing data analysis technology based on big data analysis

The Application of Elastic Network Algorithm Based on Weighted Property in Clustering Analysis

RBFNN Design Based on Modified Nearest Neighbor Clustering Algorithm for Path Tracking Control

Contact Info

Product

Resources

About